# Cross-dataset Training for Class Increasing Object Detection

arXiv: https://arxiv.org/abs/2001.04621 · HTML: https://mlsanity.com/paper/2001.04621/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 14 Jan 2020.

## Built on by (most cited first, 7 of 7)

- [Cross-Dataset Collaborative Learning for Semantic Segmentation in Autonomous Driving](https://mlsanity.com/paper/2103.11351/) (2021)
- [LMSeg: Language-guided Multi-dataset Segmentation](https://mlsanity.com/paper/2302.13495/) (2023)
- [OmDet: Large-scale vision-language multi-dataset pre-training with multimodal detection network](https://mlsanity.com/paper/2209.05946/) (2022)
- [Non-iterative optimization of pseudo-labeling thresholds for training object detection models from multiple datasets](https://mlsanity.com/paper/2210.10221/) (2022)
- [Cross-Dataset Gaze Estimation by Evidential Inter-intra Fusion](https://mlsanity.com/paper/2409.04766/) (2024)
- [Resolving Inconsistent Semantics in Multi-Dataset Image Segmentation](https://mlsanity.com/paper/2409.09893/) (2024)
- [A Dataset Fusion Algorithm for Generalised Anomaly Detection in Homogeneous Periodic Time Series Datasets](https://mlsanity.com/paper/2305.08197/) (2023)

## Abstract (arXiv)

We present a conceptually simple, flexible and general framework for cross-dataset training in object detection. Given two or more already labeled datasets that target for different object classes, cross-dataset training aims to detect the union of the different classes, so that we do not have to label all the classes for all the datasets. By cross-dataset training, existing datasets can be utilized to detect the merged object classes with a single model. Further more, in industrial applications, the object classes usually increase on demand. So when adding new classes, it is quite time-consuming if we label the new classes on all the existing datasets. While using cross-dataset training, we only need to label the new classes on the new dataset. We experiment on PASCAL VOC, COCO, WIDER FACE and WIDER Pedestrian with both solo and cross-dataset settings. Results show that our cross-dataset pipeline can achieve similar impressive performance simultaneously on these datasets compared with training independently.